DMCA
On fast approximate submodular minimization
| Citations: | 13 - 6 self |
BibTeX
@MISC{Jegelka_onfast,
author = {Stefanie Jegelka and Hui Lin and Jeff Bilmes},
title = {On fast approximate submodular minimization},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We are motivated by an application to extract a representative subset of machine learning training data and by the poor empirical performance we observe of the popular minimum norm algorithm. In fact, for our application, minimum norm can have a running time of about O(n 7) (O(n 5) oracle calls). We therefore propose a fast approximate method to minimize arbitrary submodular functions. For a large subclass of submodular functions, the algorithm is exact. Other submodular functions are iteratively approximated by tight submodular upper bounds, and then repeatedly optimized. We show theoretical properties, and empirical results suggest significant speedups over minimum norm while retaining higher accuracies.
Keyphrases
fast approximate submodular minimization minimum norm submodular function fast approximate method large sub-class significant speedup empirical result theoretical property running time representative subset tight submodular upper bound popular minimum norm algorithm training data arbitrary submodular function poor empirical performance
